Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

LLM Stats (WritingBench) — leaderboard

Metric: Score (%). Source: llm-stats.com. 15 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B (Thinking)88.3
2Qwen 3 Next 80B A3B Instruct87.3
3Qwen 3 VL 235B A22B (Thinking)86.7
4Qwen 3 VL 32B (Thinking)86.2
5Qwen 3 VL 235B A22B Instruct85.5
6Qwen 3 VL 8B (Thinking)85.5
7Qwen 3 235B A22B 2507 Instruct85.2
8Qwen 3 VL 30B A3B (Thinking)85.2
9Qwen 3 Next 80B A3B (Thinking)84.6
10Qwen 3 VL 4B (Thinking)84
11Qwen 3 VL 8B Instruct83.1
12Qwen 3 VL 32B Instruct82.9
13Qwen 3 VL 30B A3B Instruct82.6
14Qwen 3 VL 4B Instruct82.5

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-writingbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.